Sample size: How much is enough?

Austin, Homer W.

doi:10.1007/bf00167586

Cited by 7 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in databases, the size of the results for a given query was predicted using random sampling [36,40,55]. Other works focused on computing the optimal bound for the number of samples needed for satisfying a predefined error metric [4,21,33]. Furthermore, efficient sampling techniques have been developed to address the limited computational resources availability for analysing large datasets [59].…”

Section: Background and Related Workmentioning

confidence: 99%

White Box: On the Prediction of Collaborative Filtering Recommendation Systems’ Performance

Paun

Moshfeghi

Ntarmos

2023

ACM Trans. Internet Technol.

View full text Add to dashboard Cite

Collaborative Filtering recommendation algorithms (CF) are a popular solution to the information overload problem, aiding users in the item selection process. Relevant research has long focused on refining and improving these models to produce better (more effective) recommendations, and has converged on a methodology to predict their effectiveness on target datasets by evaluating them on random samples of the latter. However, predicting the efficiency of the solutions – especially with regards to their time- and resource-hungry training phase, whose requirements dwarf those of the prediction/recommendation phase – has received little to no attention in the literature. This paper addresses this gap for a number of representative and highly popular CF models, including algorithms based on matrix factorisation, k-nearest neighbours, co-clustering, and slope one schemes. To this end, we first study the computational complexity of the training phase of said CF models and derive time and space complexity equations. Then, using characteristics of the input and the aforementioned equations, we contribute a methodology for predicting the processing time and memory usage of their training phase. Our contributions further include an adaptive sampling strategy, to address the trade-off between resource usage costs and prediction accuracy, and a framework which quantifies both the efficiency and effectiveness of CF. Finally, a systematic experimental evaluation demonstrates that our method outperforms state-of-the-art regression schemes by a considerable margin, with an overhead that is a small fraction of the overall requirements of CF training.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

White Box: On the Prediction of Collaborative Filtering Recommendation Systems’ Performance

Paun

Moshfeghi

Ntarmos

2023

ACM Trans. Internet Technol.

View full text Add to dashboard Cite

show abstract

“…Thus, in this study, 10 composite water samples were collected, each comprised of a mix of 3 separate samples collected at either stream bank or spring diametric, and the middle of a sample location (Figure 2). For reasons articulated earlier in this section, 30 samples were considered adequate for this study [21,22].…”

Section: Quality Control Analysis Sampling Framementioning

confidence: 99%

Determination of Potentially Harmful Element (PHE) Distribution in Water Bodies in Krugersdorp, a Mining City in the West Rand, Gauteng Province, South Africa

et al. 2021

View full text Add to dashboard Cite

The town of Krugersdorp in South Africa is the locus of an important wildlife game reserve, the Krugersdorp Game Reserve (KGR), which is juxtaposed by the (<1000 m) down-gradient of the large-scale gold mining outfits of Mintails Mogale Gold (MMG) and Rand Uranium (RU). The aim of the study was to determine the concentration levels of potentially harmful elements (PHEs) that have accumulated due to post-mining activities in the local water bodies in Krugersdorp and to use these data as a prerequisite and basis for formulation of the most appropriate remediation measures. Thirty water samples were collected and analysed in situ for: water temperature, pH, dissolved oxygen (mgl−1), dissolved oxygen (%), total dissolved solids (TDS), oxidation/reduction potential (ORP), and electrical conductivity (EC). This was later followed by laboratory analyses of aliquots of the water samples by ICP-MS for twelve PHEs whose concentration ranges were: As (0.70–32.20), Ag (0.16–105.00), Al (1.00–41.00), Co (0.07–6.16), Cr (1.60–5.00), Cu (0.80–8.00), Fe (23.00–117.00), Mn (0.14–12 255.00), Ni (0.20–7.00), Pb (0.80–6.30), V (1.90–55.20), and Zn (2.20–783.00). Areas of the town where excessive concentration levels of these elements have negatively impacted the health of its wildlife population and surrounding ecosystems are identified, and credible mitigation measures proffered.

show abstract

Determining the factors that affect the uses of Mobile Cloud Learning (MCL) platform Blackboard- a modification of the UTAUT model

Sultana

2019

Educ Inf Technol

View full text Add to dashboard Cite

Sample size: How much is enough?

Cited by 7 publications

References 1 publication

White Box: On the Prediction of Collaborative Filtering Recommendation Systems’ Performance

White Box: On the Prediction of Collaborative Filtering Recommendation Systems’ Performance

Determination of Potentially Harmful Element (PHE) Distribution in Water Bodies in Krugersdorp, a Mining City in the West Rand, Gauteng Province, South Africa

Determining the factors that affect the uses of Mobile Cloud Learning (MCL) platform Blackboard- a modification of the UTAUT model

Contact Info

Product

Resources

About